Fei Shen

R-Genie: Reasoning-Guided Generative Image Editing

IMAGEdit: Let Any Subject Transform

PathXfer: Few-Shot Visual Fidelity Transfer for Compressed Multi-to-Few Step Sampling

Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model

Ensembling Diffusion Models via Adaptive Feature Aggregation

FaceShot: Bring Any Character into Life

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model